knitr::opts_chunk$set(echo = TRUE)
# install.packages("plotly")
# install.packages("tidyverse")
# install.packages("styler")
library(tidyverse)
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.3.6      ✔ purrr   0.3.4 
## ✔ tibble  3.1.8      ✔ dplyr   1.0.10
## ✔ tidyr   1.2.1      ✔ stringr 1.4.1 
## ✔ readr   2.1.2      ✔ forcats 0.5.2 
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
library(plotly)
## 
## Attaching package: 'plotly'
## 
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## 
## The following object is masked from 'package:stats':
## 
##     filter
## 
## The following object is masked from 'package:graphics':
## 
##     layout
library(styler)

Complete the following analysis in R and generate an RMarkdown report to show the analysis and results:

Read in the gapminder_clean.csv data as a tibble using read_csv

# gapminder # note the rows column was unlabeled - X1 for now
gapminder <- read_csv("gapminder_clean.csv") %>%
  as_tibble()
## New names:
## Rows: 2607 Columns: 20
## ── Column specification
## ──────────────────────────────────────────────────────── Delimiter: "," chr
## (2): Country Name, continent dbl (18): ...1, Year, Agriculture, value added (%
## of GDP), CO2 emissions (me...
## ℹ Use `spec()` to retrieve the full column specification for this data. ℹ
## Specify the column types or set `show_col_types = FALSE` to quiet this message.
## • `` -> `...1`


Filter the data to include only rows where Year is 1962 and then make a scatter plot comparing ‘CO2 emissions (metric tons per capita)’ and gdpPercap for the filtered data.

gapminder1962 <- gapminder %>%
  filter(Year == 1962)
ggplot(gapminder1962, aes(`CO2 emissions (metric tons per capita)`, gdpPercap)) +
  geom_point() +
  ylab("GDP per capita ($)") +
  coord_flip()
## Warning: Removed 151 rows containing missing values (geom_point).


On the filtered data, calculate the correlation of ‘CO2 emissions (metric tons per capita)’ and gdpPercap. What is the correlation and associated p value?

# coorlation test
gapminder1962_cor <- cor.test(gapminder1962$`CO2 emissions (metric tons per capita)`, gapminder1962$gdpPercap, use = "complete.obs")
gapminder1962_p <- gapminder1962_cor$p.value %>%
  signif(3)
gapminder1962_c <- gapminder1962_cor$estimate %>%
  round(2)
pearson_output <- paste0("Pearson correlation: ", gapminder1962_c, "\n")
pvalue_output <- paste0("P-value: ", gapminder1962_p)

Pearson correlation: 0.93

P-value: 1.13e-46


On the unfiltered data, answer “In what year is the correlation between ‘CO2 emissions (metric tons per capita)’ and gdpPercap the strongest?” Filter the dataset to that year for the next step…

# Find strongest correlation
years <- gapminder$Year %>% unique()
coors <- c()
for (y in years) {
  gapminderyear <- gapminder %>%
    filter(Year == y)
  gap_cor <- cor.test(gapminderyear$`CO2 emissions (metric tons per capita)`, gapminderyear$gdpPercap, use = "complete.obs") %>%
    .$estimate %>%
    round(3)
  cat(paste0(y, " pearson correlation: ", gap_cor, "\n"))
  coors <- c(coors, gap_cor)
}
## 1962 pearson correlation: 0.926
## 1967 pearson correlation: 0.939
## 1972 pearson correlation: 0.843
## 1977 pearson correlation: 0.793
## 1982 pearson correlation: 0.817
## 1987 pearson correlation: 0.81
## 1992 pearson correlation: 0.809
## 1997 pearson correlation: 0.808
## 2002 pearson correlation: 0.801
## 2007 pearson correlation: 0.72
max_year <- years[coors == max(coors)]
max_year_output <- paste0("\n", "Correlation is strongest in ", max_year)

Correlation is strongest in 1967


Using plotly, create an interactive scatter plot comparing ‘CO2 emissions (metric tons per capita)’ and gdpPercap, where the point size is determined by pop (population) and the color is determined by the continent. You can easily convert any ggplot plot to a plotly plot using the ggplotly() command.

plot1 <- gapminder %>%
  filter(Year == max_year) %>%
  ggplot(aes(x = `CO2 emissions (metric tons per capita)`, y = gdpPercap, size = pop, color = continent)) +
  geom_point() +
  ylab("GDP per capita ($)") +
  coord_flip()
ggplotly(plot1)



Now, without further guidance, use your R Data Science skills (and appropriate statistical tests) to answer the following (use the unfiltered dataset):

1. What is the relationship between continent and ‘Energy use (kg of oil equivalent per capita)’? (stats test needed)

# Filter out NAs
gapminder2 <- gapminder %>%
  filter(
    !is.na("Energy use (kg of oil equivalent per capita)"),
    !is.na(continent)
  ) %>%
  rename(energy = "Energy use (kg of oil equivalent per capita)")

# Run anova (appropriate for quantitative data organized in over 2 categories)
gapminder_aov <- aov(energy ~ continent, data = gapminder2, na.action = na.omit) %>%
  summary()
# gapminder_aov[[1]]
gapminder_aovP <- gapminder_aov[[1]][1, 5]


# Plot boxplots
ggplot(gapminder2, aes(continent, energy)) +
  # geom_violin() +
  geom_boxplot() +
  ylab("Energy use (kg of oil equivalent per capita)")
## Warning: Removed 436 rows containing non-finite values (stat_boxplot).

# answer
energy_output <- paste("A: There are big differences in energy use across the 5 continents. This can be seen in the boxplots and is highly significant by ANOVA (appropriate for quantitative data organized in over 2 categories). p-value:", gapminder_aovP)

A: There are big differences in energy use across the 5 continents. This can be seen in the boxplots and is highly significant by ANOVA (appropriate for quantitative data organized in over 2 categories). p-value: 8.52700348715528e-39


2. Is there a significant difference between Europe and Asia with respect to ‘Imports of goods and services (% of GDP)’ in the years after 1990? (stats test needed)

gapminder1990 <- gapminder %>%
  filter(Year > 1990, (continent == "Asia" | continent == "Europe"))

# Run t-test (appropriate to compare between two categories of quantitative data)
test_output <- t.test(
  filter(gapminder1990, continent == "Asia")$`Imports of goods and services (% of GDP)`,
  filter(gapminder1990, continent == "Europe")$`Imports of goods and services (% of GDP)`
)
ggplot(gapminder1990, aes(continent, `Imports of goods and services (% of GDP)`)) +
  geom_boxplot()
## Warning: Removed 12 rows containing non-finite values (stat_boxplot).

output <- paste("A: There is not a significant difference between the two, as seen in the boxplot and quantified by t.test (appropriate to compare between two categories of quantitative data). p-value:", test_output$p.value)

A: There is not a significant difference between the two, as seen in the boxplot and quantified by t.test (appropriate to compare between two categories of quantitative data). p-value: 0.177569118980769


3. What is the country (or countries) that has the highest ‘Population density (people per sq. km of land area)’ across all years? (i.e., which country has the highest average ranking in this category across each time point in the dataset?)

### Average for each country ###
gapminder_countries <- gapminder %>%
  group_by(`Country Name`) %>%
  summarise_at(vars(`Population density (people per sq. km of land area)`), list(avg_density = mean)) %>%
  arrange(desc(avg_density))
# print head and plot
# gapminder_countries %>% head()
plot1 <- ggplot(gapminder_countries, aes(x = `Country Name`, y = avg_density)) +
  geom_col() +
  theme(axis.text.x = element_blank()) +
  xlab("Countries")
ggplotly(plot1)
## Warning: Removed 9 rows containing missing values (position_stack).
### Rank across each country and plot ##

# make blank df
gapminder_countries_rank <- gapminder %>%
  mutate(rank = 1) %>%
  filter(rank == 2)
# Rank countries each year
for (y in years) {
  gapminder1 <- gapminder %>%
    filter(Year == y) %>%
    mutate(rank = rank(-`Population density (people per sq. km of land area)`))
  head(gapminder1)
  gapminder_countries_rank <- rbind(gapminder_countries_rank, gapminder1)
}

# Average for each country
gapminder_countries_rank <- gapminder_countries_rank %>%
  group_by(`Country Name`) %>%
  summarise_at(vars(rank), list(avg_density_rank = mean)) %>%
  arrange(avg_density_rank)
# print head
# gapminder_countries_rank %>% head()

output <- paste0("A: The highest average across all years is ", gapminder_countries[1, ]$`Country Name`, ". However, the highest average RANKING (rank 1-263, averaged across the 10 years of data, if they exist for the country) is a tie between these two countries: ", gapminder_countries_rank[1, ]$`Country Name`, " and ", gapminder_countries_rank[2, ]$`Country Name`)

A: The highest average across all years is Macao SAR, China. However, the highest average RANKING (rank 1-263, averaged across the 10 years of data, if they exist for the country) is a tie between these two countries: Macao SAR, China and Monaco


4. What country (or countries) has shown the greatest increase in ‘Life expectancy at birth, total (years)’ since 1962?

# List countries, set baseline in 1962
countries <- gapminder$`Country Name` %>% unique()
gapminder1962 <- filter(gapminder, Year == 1962, !is.na(`Life expectancy at birth, total (years)`))
gapminder_exp <- mutate(gapminder, Life_expectancy_vs_1962 = 1) %>%
  filter(Life_expectancy_vs_1962 == 2)

# Make new dataframe with life exp vs 1962
for (c in countries) {
  exp1962 <- filter(gapminder1962, `Country Name` == c)[1, ]
  gapminder_exp1 <- filter(gapminder, `Country Name` == c) %>%
    mutate(Life_expectancy_vs_1962 = `Life expectancy at birth, total (years)` - exp1962$`Life expectancy at birth, total (years)`)
  gapminder_exp <- rbind(gapminder_exp, gapminder_exp1)
}

# Plot
plot1 <- gapminder_exp %>%
  ggplot(aes(x = Year, y = Life_expectancy_vs_1962, color = `Country Name`)) +
  geom_line() +
  ylab("Life expectancy change since 1962 (years)")
ggplotly(plot1)
# Extract top value
gapminder_exp_top <- gapminder_exp %>%
  arrange(desc(Life_expectancy_vs_1962))

output <- paste(gapminder_exp_top[1, ]$`Country Name`, "has shown the greatest increase in life expectancy.")

Maldives has shown the greatest increase in life expectancy.